biopipen 0.31.6__py3-none-any.whl → 0.31.7__py3-none-any.whl

biopipen/__init__.py

@@ -1 +1 @@
-__version__ = "0.31.6"
+__version__ = "0.31.7"

biopipen/ns/bam.py

@@ -301,3 +301,31 @@ class BamSampling(Proc):
         "sort_args": [],
     }
     script = "file://../scripts/bam/BamSampling.py"
+
+
+class BamSubsetByBed(Proc):
+    """Subset bam file by the regions in a bed file
+
+    Input:
+        bamfile: The bam file
+        bedfile: The bed file
+
+    Output:
+        outfile: The output bam file
+
+    Envs:
+        ncores: Number of cores to use
+        samtools: Path to samtools executable
+        tool: The tool to use, currently only "samtools" is supported
+        index: Whether to index the output bam file
+    """
+    input = "bamfile:file, bedfile:file"
+    output = "outfile:file:{{in.bamfile | stem}}-subset.bam"
+    lang = config.lang.python
+    envs = {
+        "ncores": config.misc.ncores,
+        "samtools": config.exe.samtools,
+        "tool": "samtools",
+        "index": True,
+    }
+    script = "file://../scripts/bam/BamSubsetByBed.py"

biopipen/ns/bed.py

@@ -198,3 +198,43 @@ class BedtoolsIntersect(Proc):
         "postcmd": None,
     }
     script = "file://../scripts/bed/BedtoolsIntersect.py"
+
+
+class BedtoolsMakeWindows(Proc):
+    """Make windows from a BED file or genome size file, using `bedtools makewindows`.
+
+    Input:
+        infile: The input BED file or a genome size file
+            Type will be detected by the number of columns in the file.
+            If it has 3+ columns, it is treated as a BED file, otherwise
+            a genome size file.
+
+    Output:
+        outfile: The output BED file
+
+    Envs:
+        bedtools: The path to bedtools
+        window (type=int): The size of the windows
+        step (type=int): The step size of the windows
+        nwin (type=int): The number of windows to be generated
+            Exclusive with `window` and `step`.
+            Either `nwin` or `window` and `step` should be provided.
+        reverse (flag): Reverse numbering of windows in the output
+        name (choice): How to name the generated windows/regions
+            - none: Do not add any name
+            - src: Use the source interval's name
+            - winnum: Use the window number
+            - srcwinnum: Use the source interval's name and window number
+    """  # noqa: E501
+    input = "infile:file"
+    output = "outfile:file:{{in.infile | stem}}_windows.bed"
+    lang = config.lang.python
+    envs = {
+        "bedtools": config.exe.bedtools,
+        "window": None,
+        "step": None,
+        "nwin": None,
+        "reverse": False,
+        "name": "none",
+    }
+    script = "file://../scripts/bed/BedtoolsMakeWindows.py"

biopipen/scripts/bam/BamSubsetByBed.py

@@ -0,0 +1,38 @@
+from pathlib import Path
+from biopipen.utils.misc import run_command, logger
+
+# using:
+# samtools view --subsample 0.1 --subsample-seed 1234 --threads 4 -b -o out.bam in.bam
+
+bamfile = {{ in.bamfile | repr }} # pyright: ignore # noqa
+bedfile = {{ in.bedfile | repr }} # pyright: ignore # noqa
+outfile = Path({{ out.outfile | repr }}) # pyright: ignore
+ncores = {{ envs.ncores | int }} # pyright: ignore
+samtools = {{ envs.samtools | repr }} # pyright: ignore
+tool = {{ envs.tool | repr }} # pyright: ignore
+should_index = {{ envs.index | repr }} # pyright: ignore
+
+if tool != "samtools":
+    raise ValueError(
+        f"Tool {tool} is not supported. "
+        "Currently only samtools is supported."
+    )
+
+cmd = [
+    samtools,
+    "view",
+    "--target-file",
+    bedfile,
+    "-b",
+    "--threads",
+    ncores,
+    "-o",
+    outfile,
+    bamfile
+]
+run_command(cmd, fg=True)
+
+if should_index:
+    logger.info("Indexing the output bam file.")
+    cmd = [samtools, "index", "-@", ncores, outfile]
+    run_command(cmd, fg=True)

biopipen/scripts/bed/BedtoolsMakeWindows.py

@@ -0,0 +1,47 @@
+from pathlib import Path
+from biopipen.utils.misc import run_command, logger
+
+infile = Path({{in.afile | repr}})  # pyright: ignore # noqa: #999
+outfile = Path({{in.bfile | repr}})  # pyright: ignore
+bedtools = {{envs.bedtools | repr}}  # pyright: ignore
+window = {{envs.window | repr}}  # pyright: ignore
+step = {{envs.step | repr}}  # pyright: ignore
+nwin = {{envs.nwin | repr}}  # pyright: ignore
+reverse = {{envs.reverse | repr}}  # pyright: ignore
+name = {{envs.name | repr}}  # pyright: ignore
+
+if nwin is None and window is None:
+    raise ValueError("Either `nwin` or `window` should be provided.")
+
+if nwin is not None and window is not None:
+    raise ValueError("Either `nwin` or `window` should be provided, not both.")
+
+# detect if infile is a genome size file or a bed file
+with infile.open() as f:
+    line = f.readline().strip()
+    if len(line.split("\t")) > 2:
+        is_bed = True
+    else:
+        is_bed = False
+
+if is_bed:
+    logger.info("BED file is detected as input.")
+    cmd = [bedtools, "makewindows", "-b", infile]
+else:
+    logger.info("Genome size file is detected as input.")
+    cmd = [bedtools, "makewindows", "-g", infile]
+
+if nwin:
+    cmd.extend(["-n", nwin])
+elif step is not None:
+    cmd.extend(["-w", window, "-s", step])
+else:
+    cmd.extend(["-w", window])
+
+if reverse:
+    cmd.append("-reverse")
+
+if name != "none":
+    cmd.extend(["-name", name])
+
+run_command(cmd, stdout=outfile)

{biopipen-0.31.6.dist-info → biopipen-0.31.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: biopipen
-Version: 0.31.6
+Version: 0.31.7
 Summary: Bioinformatics processes/pipelines that can be run from `pipen run`
 License: MIT
 Author: pwwang

{biopipen-0.31.6.dist-info → biopipen-0.31.7.dist-info}/RECORD

@@ -1,4 +1,4 @@
-biopipen/__init__.py,sha256=KU7MsdICtcB5jVm5DAaNainBCUqYItaZLSuj12ONgkE,23
+biopipen/__init__.py,sha256=APQVRwZptBFPacKCHqg_tW4g4--qdUtMJoA6GprSuSI,23
 biopipen/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 biopipen/core/config.py,sha256=edK5xnDhM8j27srDzsxubi934NMrglLoKrdcC8qsEPk,1069
 biopipen/core/config.toml,sha256=7IXvviRicZ2D1h6x3BVgbLJ96nsh-ikvZ0sVlQepqFE,1944
@@ -7,8 +7,8 @@ biopipen/core/filters.py,sha256=5bZsbpdW7DCxqiteRdb2gelmXvfqWPmPsFxrpHdWsoE,1298
 biopipen/core/proc.py,sha256=60lUP3PcUAaKbDETo9N5PEIoeOYrLgcSmuytmrhcx8g,912
 biopipen/core/testing.py,sha256=lZ_R5ZbYPO2NPuLHdbzg6HbD_f4j8paVVbyeUqwg6FE,3411
 biopipen/ns/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-biopipen/ns/bam.py,sha256=-xVagotsURyOtwKzv72L-2f9P7467OVzgvP96syfHZc,10628
-biopipen/ns/bed.py,sha256=HsTCJge7XNfCZyCBJ4iifNKQ5we4VZSpRx8XL8--y5A,6689
+biopipen/ns/bam.py,sha256=OtvzEadx-zpr98PoZoozbQszcQBvtFDMuAtuwH-3JUw,11394
+biopipen/ns/bed.py,sha256=EqpSa7Hx6GImvJNghtV4uDo2PnPXeUt1Yq9AFWJP9_8,8159
 biopipen/ns/cellranger.py,sha256=yPBoNzVSY74J7uyVucaob5lqZKKru5-hYSM4f4Nr2OY,5553
 biopipen/ns/cellranger_pipeline.py,sha256=EWkPJTujamNSMQoRnKfhUiIj6TkMfRmCSUbPfd8Tv8E,4011
 biopipen/ns/cnv.py,sha256=ssQAHf2MB675avoXVRkYy0vGiqIpRpRExywjhbymmBI,7811
@@ -79,6 +79,7 @@ biopipen/reports/vcf/TruvariConsistency.svelte,sha256=BBvtxi1EPmGH7j5M5zMOcLEhKW
 biopipen/scripts/bam/BamMerge.py,sha256=Gd5P8V-CSsTAA8ZrUxetR-I49GjJ3VJNjrqu7-EZwXQ,3642
 biopipen/scripts/bam/BamSampling.py,sha256=Pi6CXAbBFVRGh8-0WrkB-3v3oxinfahQk11H0IdBNmQ,2312
 biopipen/scripts/bam/BamSplitChroms.py,sha256=b7GS2I4X0dLOhlPg_r9-buoIHTWlq6zHI3Rox94LXR8,4893
+biopipen/scripts/bam/BamSubsetByBed.py,sha256=QpY6WDJfbO3k2FdMyfgstFKgTdtOc1beGoUF5FI5EAc,1027
 biopipen/scripts/bam/CNAClinic.R,sha256=mQXwtShL54HZXGCPqgPKPrU74_6K_8PqtOtG0mgA-F0,5062
 biopipen/scripts/bam/CNVpytor.py,sha256=hOUli9BDMOoth0or-tjUYC1AP3yNOuxUS6G3Rhcg99s,18000
 biopipen/scripts/bam/ControlFREEC.py,sha256=oX6iWsos-CfiT_ViDBrKeMOOIVdCKWrB-_MqzLgEF9s,3267
@@ -86,6 +87,7 @@ biopipen/scripts/bed/Bed2Vcf.py,sha256=u0mp_2Y4UtEA839zq9UENesH6Gyiwd4sZQW9wFnBV
 biopipen/scripts/bed/BedConsensus.py,sha256=gfAxuIalvCEpS0tiOyAJGPYGgHN0L-hm0K37Iteh5yw,2386
 biopipen/scripts/bed/BedLiftOver.sh,sha256=Y4gBsz9w4zhE29UmWojO6F4PXMMMWC1uCzjrxa19eOs,256
 biopipen/scripts/bed/BedtoolsIntersect.py,sha256=sFyXPL3kG59xa5eJwHumcQLw3lfabOXsq2-k8IgIqt4,1722
+biopipen/scripts/bed/BedtoolsMakeWindows.py,sha256=Ip4U0ORXti65g7znZeHEbvw2PGlCxoEfeucZmw4wb1o,1428
 biopipen/scripts/bed/BedtoolsMerge.py,sha256=7mt307V_wWa_ME0VfuMsVX0HgEwfDcZtY_bDvOPjFiQ,368
 biopipen/scripts/cellranger/CellRangerCount.py,sha256=b9kkHPpq-bFh-3XCUdxdMKg3SsZmEzZFrG3dbtb4fX8,2875
 biopipen/scripts/cellranger/CellRangerSummary.R,sha256=mVOCIHngEpJIKVD3tMG5UWqS0OQGGjY6yx6ikRcqQU4,11067
@@ -284,7 +286,7 @@ biopipen/utils/reference.py,sha256=oi5evicLwHxF0KAIPNZohBeHJLJQNWFJH0cr2y5pgcg,5
 biopipen/utils/rnaseq.R,sha256=Ro2B2dG-Z2oVaT5tkwp9RHBz4dp_RF-JcizlM5GYXFs,1298
 biopipen/utils/single_cell.R,sha256=pJjYP8bIZpNAtTQ32rOXhZxaM1Y-6D-xUcK3pql9tbk,4316
 biopipen/utils/vcf.py,sha256=ajXs0M_QghEctlvUlSRjWQIABVF02wPdYd-0LP4mIsU,9377
-biopipen-0.31.6.dist-info/METADATA,sha256=2NGpF5QMNq7lG0y8MQIGpfFYyRE9lYz17RpF6dEtq0k,882
-biopipen-0.31.6.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-biopipen-0.31.6.dist-info/entry_points.txt,sha256=BYqHGBQJxyFDNLYqgH64ycI5PYwnlqwYcCFsMvJgzAU,653
-biopipen-0.31.6.dist-info/RECORD,,
+biopipen-0.31.7.dist-info/METADATA,sha256=dmsDb7Q7iTWvkZjChqUgVqhb2CiQP4j8OA0jBzRYgGY,882
+biopipen-0.31.7.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+biopipen-0.31.7.dist-info/entry_points.txt,sha256=BYqHGBQJxyFDNLYqgH64ycI5PYwnlqwYcCFsMvJgzAU,653
+biopipen-0.31.7.dist-info/RECORD,,